New AI Models (Last Year) — Page 113

qwen3_1.7b_sft_final

Qwen3-0.6B-Hanabi-SFT

base

merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.3_linear

merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.3_linear

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.7_linear

meta-llama_Llama-3.2-3B-Instruct-GRPO-vanilla_G_4-checkpoint-186

merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.9_linear

merge_cosfmt_MRL4096_ROLLOUT4_LR2e-6_w0.7_linear

merge_cosfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_linear

merge_cosfmt_MRL4096_ROLLOUT4_LR2e-6_w0.1_linear

ee_gol_grp_f1_form

SynGen-14B

chinese-reverse-sft-n100

qwen-recipe-merged

affine-ana1-11

16b_SFT

4b_SFT

qwen7b_kodcode_grpo_step180

affine-g15-5EhM3q9z5Yj4Vf2sgUSEbBTuqCvdMqQvFrnA3N9ZHnbxv7jG

qwen3_1.7b_new_standard_A_sft_overfit_lr_5e_6__global_step_192

qwen3_1.7b_new_standard_C_sft_overfit_lr_5e_6__global_step_888

qwen317step300

2b_RL_DAPO

affine-1-5ETyoog2ttXGSu5UhxhrLtjdL1BSbo2SeELdFAp1YBimQuq9

affine-v-9-5EWSasAgABTaNwkLMudKKCZw8WZKbiNMcQrHKUUMwMoWsxRj

qwen-0.5b-reasoning-v2

binary_cosfmt_MRL4096_ROLLOUT4_LR5e-7_step54

agentic-futoshiki-NonMarkov_qwen2.5-3B-5e-6_gt-SFT_20k

agentic-sudoku-NonMarkov_qwen2.5-3B-5e-6_9x9_6-6_gt-SFT_ans1-7k

llama32-1b-og-dpo-hh

Qwen3-4B-Instruct-2507-SFT-wothink-1874

ds-svd-muon-adam-1e-6-global_step_80

pdalma_ctx4_dm1_ce0_pr1_ptll32-1b_s2_ckpt_1_of_10_it4

ds1p5b_skywork_math_hard-global_step_300

qwen3_1.7b_rush_hour_multi_move_final_short_4_9

Qwen3-0.6B-Gensyn-Swarm-pesty_ferocious_fish

affine-finaltest-2

Qwen3-4B-Chess-FullFinetune-SpecialTokens

pdcd200_cptq15_ce003_pr0_ptq25-15b_omi_c100k_200tok_s8_ckpt_8_of_10_it663

pdcd200_cptq15_ce01_pr05_ptq25-15b_omi_c100k_200tok_s8_ckpt_2_of_10_it26

qwen3-4b-llm1-fds-merged